1 code implementation • 21 Feb 2024 • Lucas Lehnert, Sainbayar Sukhbaatar, DiJia Su, Qinqing Zheng, Paul McVay, Michael Rabbat, Yuandong Tian
We fine tune this model to obtain a Searchformer, a Transformer model that optimally solves previously unseen Sokoban puzzles 93. 7% of the time, while using up to 26. 8% fewer search steps than the $A^*$ implementation that was used for training initially.
no code implementations • 2 Feb 2022 • Paul McVay, Dr. Tie Liu, Dr. Krishna Narayanan
In this paper, we show that linear separability is maintained as long as the distortion of the inner products is smaller than the squared margin of the original data-generating distribution.